Upload README.md

README.md

@@ -3,8 +3,8 @@ title: ML Model Trainer
 emoji: 🤖
 colorFrom: blue
 colorTo: green
-sdk: gradio
-sdk_version: 4.44.0
+sdk: streamlit
+sdk_version: 1.28.0
 app_file: app.py
 pinned: false
 ---
@@ -16,16 +16,15 @@ Free tool to generate training scripts for fine-tuning open-source LLMs.
 ## Features
 
 - **SFT** (Supervised Fine-Tuning) - Full model fine-tuning
-- **DPO** (Direct Preference Optimization) - Preference alignment
+- **DPO** (Direct Preference Optimization) - Preference alignment  
 - **LoRA** - Parameter-efficient fine-tuning
 
 ## Supported Models
 
 | Size | Models |
 |------|--------|
-| Small (0.5-1.5B) | Qwen2.5-0.5B, Qwen2.5-1.5B, Phi-3-mini, Gemma-2B, Llama-3.2-1B |
+| Small (0.5-1.5B) | Qwen2.5-0.5B, Qwen2.5-1.5B, Llama-3.2-1B, Phi-3-mini, Gemma-2B |
 | Medium (7B) | Qwen2.5-7B, Llama-3.2-3B, Mistral-7B |
-| Large (14B+) | Qwen2.5-14B, Mixtral-8x7B |
 
 ## Public Datasets
 
@@ -33,7 +32,6 @@ Free tool to generate training scripts for fine-tuning open-source LLMs.
 - openai/gsm8k
 - meta-math/MATH
 - anthropic/hh-rlhf
-- stanfordnlp/SHP
 
 ## How to Use